Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/eveld/claude/share-docsnpx skills add eveld/claude --skill share-docsgit clone --depth 1 https://github.com/eveld/claudeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00017 | $0.01116 |
| Opus 5 | $0.00009 | $0.00558 |
| Sonnet 5 | $0.00003 | $0.00223 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
share-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Share Documents
Promote personal documents to the shared namespace for team collaboration. This skill handles numbering, frontmatter updates, and git operations atomically.
When to Use
- When a research document is complete and ready for team review
- When a plan is finalized and ready for team implementation
- When you want to publish your work to collaborators
Workflow
1. Validate Personal Document
Check that the personal document exists and is ready to share:
- Path format:
thoughts/{username}/NNNN-slug/ - Contains required files (research.md, plan.md, etc.)
- Frontmatter is complete
- No
shared_asfield yet (not already shared)
2. Pull Latest Changes
git pull
Get latest shared documents to determine next available number.
3. Find Next Shared Number
Scan thoughts/shared/ for highest number:
NEXT_SHARED=$(ls -1 thoughts/shared/ 2>/dev/null | grep -E '^[0-9]{4}-' | sort -r | head -1 | cut -d'-' -f1 || echo "0000")
NEXT_SHARED=$(printf "%04d" $((10#${NEXT_SHARED} + 1)))
4. Copy to Shared
Copy entire personal directory to shared with new number:
# Example: thoughts/erik/0001-auth-system → thoughts/shared/0042-auth-system
cp -r thoughts/{username}/{NNNN}-{slug} thoughts/shared/${NEXT_SHARED}-{slug}
5. Update Frontmatter in Both Copies
Personal copy (thoughts/erik/0001-auth-system/research.md):
---
feature_slug: "erik/0001-auth-system"
shared_as: "0042-auth-system"
shared_date: "2026-02-04"
status: shared
# ... other fields unchanged
---
Shared copy (thoughts/shared/0042-auth-system/research.md):
---
feature_slug: "0042-auth-system"
original_slug: "erik/0001-auth-system"
shared_date: "2026-02-04"
status: published
# ... other fields unchanged
---
Update frontmatter in all markdown files within both directories (research.md, plan.md, changelog.md, etc.).
6. Commit and Push
Atomic operation to claim the shared number:
git add thoughts/shared/${NEXT_SHARED}-${slug} thoughts/${username}/${NNNN}-${slug}
git commit -m "feat: share ${slug} (was ${username}/${NNNN})"
git push
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 168 lines · 17 tokens per session scan A c060d1945f04
share-docs is a skill published in the GitHub repository eveld/claude (10 stars, last pushed 7mo ago), licensed MIT. It adds 17 tokens to every session and 1,116 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
omh-materials-package
This is a Hermes-native materials-package workflow skill.
omh-deliverable-package
This is a Hermes-native deliverable-package workflow skill.
citra
Skill "citra" from SylphxAI/pdf-reader-mcp, covering citra — pdf evidence for agents, install, or, tools and sdk.
csv-to-sif
Export a project's FF&E product-library CSV as dealer-system SIF. Use to produce a .sif schedule; use sif-to-csv for the reverse direction.
epd-parser
Extract GWP, life-cycle stages, certifications, and impact metrics from an EPD PDF. Use when given a declaration to parse; not to find or compare EPDs.
product-data-cleanup
Clean a local FF&E CSV schedule by normalizing casing, dimensions, units, language, materials, and formatting. Use when asked to clean, fix, or standardize product data.